Cover Image

EVA: Aligning Video World Models with Executable Robot Actions via Inverse Dynamics Rewards

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wang, Ruixiang, Liu, Qingming, Deng, Yueci, Liu, Guiliang, Liu, Zhen, Jia, Kui
Format:	Preprint
Published:	2026
Subjects:	Robotics Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

DexWorldModel: Causal Latent World Modeling towards Automated Learning of Embodied Tasks
by: Deng, Yueci, et al.
Published: (2026)

You Only Teach Once: Learn One-Shot Bimanual Robotic Manipulation from Video Demonstrations
by: Zhou, Huayi, et al.
Published: (2025)

PAct: Part-Decomposed Single-View Articulated Object Generation
by: Liu, Qingming, et al.
Published: (2026)

Toward Humanoid Brain-Body Co-design: Joint Optimization of Control and Morphology for Fall Recovery
by: Yue, Bo, et al.
Published: (2025)

Grounding Sim-to-Real Generalization in Dexterous Manipulation: An Empirical Study with Vision-Language-Action Models
by: Jin, Ruixing, et al.
Published: (2026)

RoboAlign-R1: Distilled Multimodal Reward Alignment for Robot Video World Models
by: Wu, Hao, et al.
Published: (2026)

GAT-Grasp: Gesture-Driven Affordance Transfer for Task-Aware Robotic Grasping
by: Wang, Ruixiang, et al.
Published: (2025)

Real-Time Verification of Embodied Reasoning for Generative Skill Acquisition
by: Yue, Bo, et al.
Published: (2025)

When to Trust Imagination: Adaptive Action Execution for World Action Models
by: Wang, Rui, et al.
Published: (2026)

NORA-1.5: A Vision-Language-Action Model Trained using World Model- and Action-based Preference Rewards
by: Hung, Chia-Yu, et al.
Published: (2025)

Exploring the Adversarial Vulnerabilities of Vision-Language-Action Models in Robotics
by: Wang, Taowen, et al.
Published: (2024)

World Action Verifier: Self-Improving World Models via Forward-Inverse Asymmetry
by: Liu, Yuejiang, et al.
Published: (2026)

From Reaction to Anticipation: Proactive Failure Recovery through Agentic Task Graph for Robotic Manipulation
by: Xu, Sheng, et al.
Published: (2026)

Instruct2Act: From Human Instruction to Actions Sequencing and Execution via Robot Action Network for Robotic Manipulation
by: Sharma, Archit, et al.
Published: (2026)

Toward Aligning Human and Robot Actions via Multi-Modal Demonstration Learning
by: Zahid, Azizul, et al.
Published: (2025)

A Vision-Language-Action-Critic Model for Robotic Real-World Reinforcement Learning
by: Zhai, Shaopeng, et al.
Published: (2025)

Bridging Scale Discrepancies in Robotic Control via Language-Based Action Representations
by: Zhang, Yuchi, et al.
Published: (2025)

Action Flow Matching for Continual Robot Learning
by: Murillo-Gonzalez, Alejandro, et al.
Published: (2025)

Recognizing Actions from Robotic View for Natural Human-Robot Interaction
by: Wang, Ziyi, et al.
Published: (2025)

Unified World Models: Coupling Video and Action Diffusion for Pretraining on Large Robotic Datasets
by: Zhu, Chuning, et al.
Published: (2025)

Multi-Task Interactive Robot Fleet Learning with Visual World Models
by: Liu, Huihan, et al.
Published: (2024)

Large Reward Models: Generalizable Online Robot Reward Generation with Vision-Language Models
by: Wu, Yanru, et al.
Published: (2026)

IRL-VLA: Training an Vision-Language-Action Policy via Reward World Model
by: Jiang, Anqing, et al.
Published: (2025)

World-Gymnast: Training Robots with Reinforcement Learning in a World Model
by: Sharma, Ansh Kumar, et al.
Published: (2026)

CLIP-Motion: Learning Reward Functions for Robotic Actions Using Consecutive Observations
by: Dang, Xuzhe, et al.
Published: (2023)

ManipDreamer: Boosting Robotic Manipulation World Model with Action Tree and Visual Guidance
by: Li, Ying, et al.
Published: (2025)

Learning to Recover: Dynamic Reward Shaping with Wheel-Leg Coordination for Fallen Robots
by: Deng, Boyuan, et al.
Published: (2025)

ChronoDreamer: Action-Conditioned World Model as an Online Simulator for Robotic Planning
by: Zhou, Zhenhao, et al.
Published: (2025)

TimeRewarder: Learning Dense Reward from Passive Videos via Frame-wise Temporal Distance
by: Liu, Yuyang, et al.
Published: (2025)

DyWA: Dynamics-adaptive World Action Model for Generalizable Non-prehensile Manipulation
by: Lyu, Jiangran, et al.
Published: (2025)

WorldVLA: Towards Autoregressive Action World Model
by: Cen, Jun, et al.
Published: (2025)

EC-Flow: Enabling Versatile Robotic Manipulation from Action-Unlabeled Videos via Embodiment-Centric Flow
by: Chen, Yixiang, et al.
Published: (2025)

Model-Based AI planning and Execution Systems for Robotics
by: Wertheim, Or, et al.
Published: (2025)

Reward Training Wheels: Adaptive Auxiliary Rewards for Robotics Reinforcement Learning
by: Wang, Linji, et al.
Published: (2025)

Off-Dynamics Reinforcement Learning via Domain Adaptation and Reward Augmented Imitation
by: Guo, Yihong, et al.
Published: (2024)

Unified Embodied VLM Reasoning with Robotic Action via Autoregressive Discretized Pre-training
by: Liu, Yi, et al.
Published: (2025)

RoboAct-CLIP: Video-Driven Pre-training of Atomic Action Understanding for Robotics
by: Zhang, Zhiyuan, et al.
Published: (2025)

EMMA: Generalizing Real-World Robot Manipulation via Generative Visual Transfer
by: Dong, Zhehao, et al.
Published: (2025)

Learning Reward for Robot Skills Using Large Language Models via Self-Alignment
by: Zeng, Yuwei, et al.
Published: (2024)

Automated Hybrid Reward Scheduling via Large Language Models for Robotic Skill Learning
by: Huang, Changxin, et al.
Published: (2025)